Skip to content

Commit

Permalink
Remove NodeExporterDeviceError alert. (#1030)
Browse files Browse the repository at this point in the history
  • Loading branch information
whites11 authored Feb 27, 2024
1 parent 886d14e commit 1aa7eb9
Show file tree
Hide file tree
Showing 4 changed files with 5 additions and 73 deletions.
4 changes: 4 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## [Unreleased]

### Removed

- Remove `NodeExporterDeviceError` alert.

## [2.152.1] - 2024-02-26

### Fixed
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -22,15 +22,3 @@ spec:
severity: page
team: {{ include "providerTeam" . }}
topic: observability
- alert: NodeExporterDeviceError
annotations:
description: '{{`NodeExporter Mountpoint {{ $labels.mountpoint }} on device {{ $labels.device }} on {{ $labels.instance }} is erroring.`}}'
opsrecipe: node-exporter-device-error/
expr: node_filesystem_device_error{mountpoint=~"(/rootfs)?/var/(log|lib/kubelet.*|lib/kubelet|lib/etcd|lib/docker|lib/containerd)",cluster_type="management_cluster"} == 1 or node_filesystem_device_error{mountpoint=~"(/rootfs)?/var/(log|lib/kubelet|lib/etcd|lib/docker|lib/containerd)",cluster_type="workload_cluster"} == 1
for: 10m
labels:
area: kaas
cancel_if_outside_working_hours: "true"
severity: page
team: {{ include "providerTeam" . }}
topic: observability
31 changes: 1 addition & 30 deletions test/tests/providers/capi/capz/node-exporter.all.rules.test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -35,33 +35,4 @@ tests:
- alertname: NodeExporterCollectorFailed
eval_time: 70m

# NodeExporterDeviceError tests
- interval: 1m
input_series:
- series: 'node_filesystem_device_error{device="/dev/mapper/usr", fstype="ext4", instance="10.0.5.111:10300", mountpoint="/var/lib/kubelet", cluster_type="workload_cluster"}'
values: "_x20 1+0x20 0+0x20"
alert_rule_test:
- alertname: NodeExporterDeviceError
eval_time: 10m
exp_alerts:
- alertname: NodeExporterDeviceError
eval_time: 20m
exp_alerts:
- alertname: NodeExporterDeviceError
eval_time: 30m
exp_alerts:
- exp_labels:
alertname: NodeExporterDeviceError
area: "kaas"
cancel_if_outside_working_hours: "true"
cluster_type: "workload_cluster"
device: "/dev/mapper/usr"
fstype: "ext4"
instance: "10.0.5.111:10300"
mountpoint: "/var/lib/kubelet"
severity: "page"
team: "phoenix"
topic: "observability"
exp_annotations:
description: "NodeExporter Mountpoint /var/lib/kubelet on device /dev/mapper/usr on 10.0.5.111:10300 is erroring."
opsrecipe: "node-exporter-device-error/"

31 changes: 0 additions & 31 deletions test/tests/providers/vintage/aws/node-exporter.all.rules.test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -34,34 +34,3 @@ tests:
opsrecipe: "node-exporter-device-error/"
- alertname: NodeExporterCollectorFailed
eval_time: 70m

# NodeExporterDeviceError tests
- interval: 1m
input_series:
- series: 'node_filesystem_device_error{device="/dev/mapper/usr", fstype="ext4", instance="10.0.5.111:10300", mountpoint="/var/lib/kubelet", cluster_type="workload_cluster"}'
values: "_x20 1+0x20 0+0x20"
alert_rule_test:
- alertname: NodeExporterDeviceError
eval_time: 10m
exp_alerts:
- alertname: NodeExporterDeviceError
eval_time: 20m
exp_alerts:
- alertname: NodeExporterDeviceError
eval_time: 30m
exp_alerts:
- exp_labels:
alertname: NodeExporterDeviceError
area: "kaas"
cancel_if_outside_working_hours: "true"
cluster_type: "workload_cluster"
device: "/dev/mapper/usr"
fstype: "ext4"
instance: "10.0.5.111:10300"
mountpoint: "/var/lib/kubelet"
severity: "page"
team: "phoenix"
topic: "observability"
exp_annotations:
description: "NodeExporter Mountpoint /var/lib/kubelet on device /dev/mapper/usr on 10.0.5.111:10300 is erroring."
opsrecipe: "node-exporter-device-error/"

0 comments on commit 1aa7eb9

Please sign in to comment.